Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
jbrinkma
/
gpt2_vs_pythia
like
0
License:
mit
Model card
Files
Files and versions
Community
3b623bd
gpt2_vs_pythia
1 contributor
History:
29 commits
jbrinkma
Upload Pythia_70M_L0_lr_0.0001_gpt_neox.layers.0.mlp_config.json with huggingface_hub
3b623bd
verified
3 months ago
.gitattributes
1.52 kB
initial commit
3 months ago
GPT2_L0_lr_0.0001_transformer.h.0.attn_checkpoint.pt
pickle
Detected Pickle imports (7)
"torch._utils._rebuild_parameter"
,
"torch.FloatStorage"
,
"collections.OrderedDict"
,
"torch._utils._rebuild_tensor_v2"
,
"src.training.config.TrainingConfig"
,
"src.autoencoders.autoencoder.UntiedSAE"
,
"__builtin__.set"
How to fix it?
18.9 MB
LFS
Upload GPT2_L0_lr_0.0001_transformer.h.0.attn_checkpoint.pt with huggingface_hub
3 months ago
GPT2_L0_lr_0.0001_transformer.h.0.attn_config.json
1.31 kB
Upload GPT2_L0_lr_0.0001_transformer.h.0.attn_config.json with huggingface_hub
3 months ago
GPT2_L0_sparsity_coefficient_0.0009_transformer.h.0.attn_checkpoint.pt
pickle
Detected Pickle imports (7)
"torch._utils._rebuild_tensor_v2"
,
"collections.OrderedDict"
,
"src.autoencoders.autoencoder.UntiedSAE"
,
"src.training.config.TrainingConfig"
,
"torch.FloatStorage"
,
"torch._utils._rebuild_parameter"
,
"__builtin__.set"
How to fix it?
18.9 MB
LFS
Upload GPT2_L0_sparsity_coefficient_0.0009_transformer.h.0.attn_checkpoint.pt with huggingface_hub
3 months ago
GPT2_L0_sparsity_coefficient_0.0009_transformer.h.0.attn_config.json
1.33 kB
Upload GPT2_L0_sparsity_coefficient_0.0009_transformer.h.0.attn_config.json with huggingface_hub
3 months ago
GPT2_L0_sparsity_coefficient_0.0027_transformer.h.0.attn_checkpoint.pt
pickle
Detected Pickle imports (7)
"src.autoencoders.autoencoder.UntiedSAE"
,
"torch._utils._rebuild_tensor_v2"
,
"__builtin__.set"
,
"src.training.config.TrainingConfig"
,
"torch._utils._rebuild_parameter"
,
"torch.FloatStorage"
,
"collections.OrderedDict"
How to fix it?
18.9 MB
LFS
Upload GPT2_L0_sparsity_coefficient_0.0027_transformer.h.0.attn_checkpoint.pt with huggingface_hub
3 months ago
GPT2_L0_sparsity_coefficient_0.0027_transformer.h.0.attn_config.json
1.33 kB
Upload GPT2_L0_sparsity_coefficient_0.0027_transformer.h.0.attn_config.json with huggingface_hub
3 months ago
GPT2_L0_sparsity_coefficient_0.0027_transformer.h.0.mlp_checkpoint.pt
pickle
Detected Pickle imports (7)
"torch._utils._rebuild_parameter"
,
"torch.FloatStorage"
,
"collections.OrderedDict"
,
"torch._utils._rebuild_tensor_v2"
,
"src.training.config.TrainingConfig"
,
"src.autoencoders.autoencoder.UntiedSAE"
,
"__builtin__.set"
How to fix it?
18.9 MB
LFS
Upload GPT2_L0_sparsity_coefficient_0.0027_transformer.h.0.mlp_checkpoint.pt with huggingface_hub
3 months ago
GPT2_L0_sparsity_coefficient_0.0027_transformer.h.0.mlp_config.json
1.33 kB
Upload GPT2_L0_sparsity_coefficient_0.0027_transformer.h.0.mlp_config.json with huggingface_hub
3 months ago
GPT2_L1_lr_0.007525_transformer.h.1.mlp_checkpoint.pt
pickle
Detected Pickle imports (7)
"collections.OrderedDict"
,
"__builtin__.set"
,
"torch._utils._rebuild_tensor_v2"
,
"torch._utils._rebuild_parameter"
,
"src.autoencoders.autoencoder.UntiedSAE"
,
"torch.FloatStorage"
,
"src.training.config.TrainingConfig"
How to fix it?
18.9 MB
LFS
Upload GPT2_L1_lr_0.007525_transformer.h.1.mlp_checkpoint.pt with huggingface_hub
3 months ago
GPT2_L1_lr_0.007525_transformer.h.1.mlp_config.json
1.33 kB
Upload GPT2_L1_lr_0.007525_transformer.h.1.mlp_config.json with huggingface_hub
3 months ago
GPT2_L1_sparsity_coefficient_0.0003_transformer.h.1.attn_checkpoint.pt
pickle
Detected Pickle imports (7)
"torch._utils._rebuild_parameter"
,
"torch.FloatStorage"
,
"collections.OrderedDict"
,
"torch._utils._rebuild_tensor_v2"
,
"src.training.config.TrainingConfig"
,
"src.autoencoders.autoencoder.UntiedSAE"
,
"__builtin__.set"
How to fix it?
18.9 MB
LFS
Upload GPT2_L1_sparsity_coefficient_0.0003_transformer.h.1.attn_checkpoint.pt with huggingface_hub
3 months ago
GPT2_L1_sparsity_coefficient_0.0003_transformer.h.1.attn_config.json
1.33 kB
Upload GPT2_L1_sparsity_coefficient_0.0003_transformer.h.1.attn_config.json with huggingface_hub
3 months ago
GPT2_L1_sparsity_coefficient_0.0009_transformer.h.1.mlp_checkpoint.pt
pickle
Detected Pickle imports (7)
"src.training.config.TrainingConfig"
,
"torch.FloatStorage"
,
"torch._utils._rebuild_parameter"
,
"torch._utils._rebuild_tensor_v2"
,
"collections.OrderedDict"
,
"__builtin__.set"
,
"src.autoencoders.autoencoder.UntiedSAE"
How to fix it?
18.9 MB
LFS
Upload GPT2_L1_sparsity_coefficient_0.0009_transformer.h.1.mlp_checkpoint.pt with huggingface_hub
3 months ago
GPT2_L1_sparsity_coefficient_0.0009_transformer.h.1.mlp_config.json
1.33 kB
Upload GPT2_L1_sparsity_coefficient_0.0009_transformer.h.1.mlp_config.json with huggingface_hub
3 months ago
GPT2_L1_sparsity_coefficient_0.0024_transformer.h.1.mlp_checkpoint.pt
pickle
Detected Pickle imports (7)
"src.training.config.TrainingConfig"
,
"torch._utils._rebuild_tensor_v2"
,
"torch._utils._rebuild_parameter"
,
"__builtin__.set"
,
"collections.OrderedDict"
,
"torch.FloatStorage"
,
"src.autoencoders.autoencoder.UntiedSAE"
How to fix it?
18.9 MB
LFS
Upload GPT2_L1_sparsity_coefficient_0.0024_transformer.h.1.mlp_checkpoint.pt with huggingface_hub
3 months ago
GPT2_L1_sparsity_coefficient_0.0024_transformer.h.1.mlp_config.json
1.35 kB
Upload GPT2_L1_sparsity_coefficient_0.0024_transformer.h.1.mlp_config.json with huggingface_hub
3 months ago
Pythia_70M_L0_lr_0.0001_gpt_neox.layers.0.mlp_checkpoint.pt
pickle
Detected Pickle imports (7)
"torch._utils._rebuild_parameter"
,
"src.autoencoders.autoencoder.UntiedSAE"
,
"torch.FloatStorage"
,
"__builtin__.set"
,
"collections.OrderedDict"
,
"src.training.config.TrainingConfig"
,
"torch._utils._rebuild_tensor_v2"
How to fix it?
8.4 MB
LFS
Upload Pythia_70M_L0_lr_0.0001_gpt_neox.layers.0.mlp_checkpoint.pt with huggingface_hub
3 months ago
Pythia_70M_L0_lr_0.0001_gpt_neox.layers.0.mlp_config.json
1.34 kB
Upload Pythia_70M_L0_lr_0.0001_gpt_neox.layers.0.mlp_config.json with huggingface_hub
3 months ago
Pythia_70M_L0_lr_0.01_gpt_neox.layers.0.mlp_checkpoint.pt
pickle
Detected Pickle imports (7)
"torch._utils._rebuild_parameter"
,
"src.autoencoders.autoencoder.UntiedSAE"
,
"torch.FloatStorage"
,
"__builtin__.set"
,
"collections.OrderedDict"
,
"src.training.config.TrainingConfig"
,
"torch._utils._rebuild_tensor_v2"
How to fix it?
8.4 MB
LFS
Upload Pythia_70M_L0_lr_0.01_gpt_neox.layers.0.mlp_checkpoint.pt with huggingface_hub
3 months ago
Pythia_70M_L0_lr_0.01_gpt_neox.layers.0.mlp_config.json
1.33 kB
Upload Pythia_70M_L0_lr_0.01_gpt_neox.layers.0.mlp_config.json with huggingface_hub
3 months ago
Pythia_70M_L0_sparsity_coefficient_0.0012_gpt_neox.layers.0.mlp_checkpoint.pt
pickle
Detected Pickle imports (7)
"src.training.config.TrainingConfig"
,
"torch._utils._rebuild_tensor_v2"
,
"__builtin__.set"
,
"torch._utils._rebuild_parameter"
,
"torch.FloatStorage"
,
"src.autoencoders.autoencoder.UntiedSAE"
,
"collections.OrderedDict"
How to fix it?
8.4 MB
LFS
Upload Pythia_70M_L0_sparsity_coefficient_0.0012_gpt_neox.layers.0.mlp_checkpoint.pt with huggingface_hub
3 months ago
Pythia_70M_L0_sparsity_coefficient_0.0012_gpt_neox.layers.0.mlp_config.json
1.37 kB
Upload Pythia_70M_L0_sparsity_coefficient_0.0012_gpt_neox.layers.0.mlp_config.json with huggingface_hub
3 months ago
Pythia_70M_L1_sparsity_coefficient_0.0015_gpt_neox.layers.1.attention_checkpoint.pt
pickle
Detected Pickle imports (7)
"torch._utils._rebuild_parameter"
,
"src.autoencoders.autoencoder.UntiedSAE"
,
"torch.FloatStorage"
,
"__builtin__.set"
,
"collections.OrderedDict"
,
"src.training.config.TrainingConfig"
,
"torch._utils._rebuild_tensor_v2"
How to fix it?
8.4 MB
LFS
Upload Pythia_70M_L1_sparsity_coefficient_0.0015_gpt_neox.layers.1.attention_checkpoint.pt with huggingface_hub
3 months ago
Pythia_70M_L1_sparsity_coefficient_0.0015_gpt_neox.layers.1.attention_config.json
1.36 kB
Upload Pythia_70M_L1_sparsity_coefficient_0.0015_gpt_neox.layers.1.attention_config.json with huggingface_hub
3 months ago
Pythia_70M_L1_sparsity_coefficient_0.0021_gpt_neox.layers.1.attention_checkpoint.pt
pickle
Detected Pickle imports (7)
"torch._utils._rebuild_parameter"
,
"src.autoencoders.autoencoder.UntiedSAE"
,
"torch.FloatStorage"
,
"__builtin__.set"
,
"collections.OrderedDict"
,
"src.training.config.TrainingConfig"
,
"torch._utils._rebuild_tensor_v2"
How to fix it?
8.4 MB
LFS
Upload Pythia_70M_L1_sparsity_coefficient_0.0021_gpt_neox.layers.1.attention_checkpoint.pt with huggingface_hub
3 months ago
Pythia_70M_L1_sparsity_coefficient_0.0021_gpt_neox.layers.1.attention_config.json
1.38 kB
Upload Pythia_70M_L1_sparsity_coefficient_0.0021_gpt_neox.layers.1.attention_config.json with huggingface_hub
3 months ago
Pythia_70M_L1_sparsity_coefficient_0.003_gpt_neox.layers.1.mlp_checkpoint.pt
pickle
Detected Pickle imports (7)
"torch._utils._rebuild_parameter"
,
"collections.OrderedDict"
,
"torch._utils._rebuild_tensor_v2"
,
"src.autoencoders.autoencoder.UntiedSAE"
,
"__builtin__.set"
,
"torch.FloatStorage"
,
"src.training.config.TrainingConfig"
How to fix it?
8.4 MB
LFS
Upload Pythia_70M_L1_sparsity_coefficient_0.003_gpt_neox.layers.1.mlp_checkpoint.pt with huggingface_hub
3 months ago
Pythia_70M_L1_sparsity_coefficient_0.003_gpt_neox.layers.1.mlp_config.json
1.35 kB
Upload Pythia_70M_L1_sparsity_coefficient_0.003_gpt_neox.layers.1.mlp_config.json with huggingface_hub
3 months ago
README.md
21 Bytes
initial commit
3 months ago
